Method, interaction device, server, and system for speech recognition
First Claim
Patent Images
1. A speech recognition method comprising:
- receiving, by a server, text from a user interactive device, where the text results from conversion of speech signals at the user interactive device and the speech signals result from a user requesting a service;
parsing, by the server, the text to obtain first target semantics;
determining, by the server, according to the obtained first target semantics, two or more third-party application objects, each third-party application object is associated with a third-party application capable of providing the requested service and not authorized to be started by speech by its third-party producer;
identifying, by the server, from a third-party application registry the third-party applications from the third-party application objects;
providing to the user the identified third-party applications;
receiving from the user a desired third party application from the identified third-party applications;
starting, by the server, the selected third-party application;
sending, by the server, a semantics command of the first target semantics to the selected third-party application; and
invoking, by the selected third-party application, in response to the semantics command of the first target semantics, an Application Programming Interface (API) that acquires and outputs a required resource for responding to the requested service.
1 Assignment
0 Petitions
Accused Products
Abstract
Embodiments of the present invention provide a method, an apparatus, and a system for speech recognition. a third-party application corresponding to a speech signal of a user can be determined according to the speech signal and by means of semantic analysis; and third-party application registry information is searched for and a third-party program is started, so that the user does not need to tap the third-party application to start the corresponding program, thereby providing more intelligent service for the user and facilitating use for the user.
19 Citations
13 Claims
-
1. A speech recognition method comprising:
-
receiving, by a server, text from a user interactive device, where the text results from conversion of speech signals at the user interactive device and the speech signals result from a user requesting a service; parsing, by the server, the text to obtain first target semantics; determining, by the server, according to the obtained first target semantics, two or more third-party application objects, each third-party application object is associated with a third-party application capable of providing the requested service and not authorized to be started by speech by its third-party producer; identifying, by the server, from a third-party application registry the third-party applications from the third-party application objects; providing to the user the identified third-party applications; receiving from the user a desired third party application from the identified third-party applications; starting, by the server, the selected third-party application; sending, by the server, a semantics command of the first target semantics to the selected third-party application; and invoking, by the selected third-party application, in response to the semantics command of the first target semantics, an Application Programming Interface (API) that acquires and outputs a required resource for responding to the requested service. - View Dependent Claims (2, 3, 4, 5, 6)
-
-
7. A device for speech recognition comprising:
-
a non-transitory memory storage comprising instructions; and a processor in communication with the memory, wherein the processor executes the instructions to; a) receiving text from a user interactive device, where the text results from conversion of speech signals at the user interactive device and the speech signals result from a user requesting a service; b) parsing the text to obtain target semantics; c) determine, according to the obtained target semantics, two or more third-party application objects, each object associated with a third-party application capable of providing the requested service and not authorized to be started by speech by its third-party producer; d) identify the third-party applications from a third party application registry associated with the determined third-party application objects; e) provide to a user the identified third-party applications; f) receive from the user a desired third party application selected from the identified third-party applications; g) start a selected one of the third-party applications in response to selection by the user of one of the identified third party applications; and h) send a semantics command of the target semantics to the selected third-party application that invokes an Application Programming Interface (API) for acquiring a resource for responding to the user requested service. - View Dependent Claims (8, 9)
-
-
10. A non-transitory, computer readable medium storing instructions for execution by a processor that cause the processor to provide the following speech recognition method:
-
receiving text from a user interactive device, where the text results from conversion of speech signals at the user interactive device and the speech signals result from a user requesting a service; parsing the text to obtain target semantics; determining, according to the target semantics obtained from parsed text created from converting speech signals to text, two or more third-party application objects, each object associated with a third-party application capable of providing the requested service and not authorized to be started by speech by its third-party producer; identifying to the user, from a third-party application registry the third-party applications from the third-party application objects; providing to a user the identified third-party applications; receiving from the user a desired third party application selected from the identified third-party applications; starting the selected third-party application in response to selection by the user of a desired third party application from the identified third party applications; and sending a semantics command of the target semantics to the selected third-party application, causing the selected third-party application to invoke an Application Programming Interface (API) that acquires a required resource for responding to the requested service. - View Dependent Claims (11, 12, 13)
-
Specification